Meng Wei
Meng Wei

AI for Science / Applied AI / AI for Health

Short Bio

I am an applied AI researcher focusing on AI for health. I want to contribute to leveraging AI to make human life better, especially through clinical AI, biomedical AI, health monitoring, and broader AI for science.

Previously, I was a fully funded PhD researcher in the Smart Medical Imaging CDT programme at King's College London. I obtained my master's degree at Imperial College London, focusing on medical imaging and robotics, and my undergraduate degree in electrical engineering from the University of Liverpool. I previously interned at Viridien, formerly CGG, as a machine learning engineer.

Research Interests

My research interests include computer vision, AI for science, multimodal models, and robotics. My current research focuses on agentic frameworks for biomedical applications.

Google Scholar LinkedIn GitHub

News

Selected Papers

On-device LLM main figure

Benchmarking and Adapting On-Device LLMs for Clinical Decision Support

Alif Munim, Omar Ibrahim, Alhusain Abdalla, Jun Ma, Meng Wei, Shuolin Yin, Leo Chen, and Bo Wang

[Paper] [GitHub]

SurgRef main figure

Where It Moves, It Matters: Referring Surgical Instrument Segmentation via Motion

Meng Wei, Kun Yuan, Shi Li, Yue Zhou, Long Bai, Nassir Navab, Hongliang Ren, Hong Joo Lee,
Tom Vercauteren, Nicolas Padoy

AAAI 2026 [Paper] [GitHub]

Prograsp forceps on the left travels around then stays idle.

Prograsp forceps is travelling around then clamping on the right.

Large needle driver is suturing tissue on the left.

Large needle driver on the right is looping tissue with the needle and thread.

SurgPIS main figure

SurgPIS: Surgical-instrument-level Instances and Part-level Semantics for Weakly-supervised Part-aware Instance Segmentation

Meng Wei, Charlie Budd, Oluwatosin Alabi, Miaojing Shi, Tom Vercauteren

[Paper] [GitHub]

SegMatch main figure

SegMatch: Semi-supervised Surgical Instrument Segmentation

Meng Wei, Charlie Budd, Luis C Garcia-Peraza-Herrera, Reuben Dorent, Miaojing Shi, Tom Vercauteren

Nature Scientific Reports 2025 [Paper]

Enhancing surgical instrument segmentation main figure

Enhancing Surgical Instrument Segmentation: Integrating Vision Transformer Insights with Adapter

Meng Wei, Miaojing Shi, Tom Vercauteren

IJCARS 2024 [Paper] [GitHub]

Text promptable surgical instrument segmentation main figure

Text promptable surgical instrument segmentation with vision-language models

Zijian Zhou, Oluwatosin Alabi, Meng Wei, Tom Vercauteren, Miaojing Shi

NeurIPS 2023 [Paper] [GitHub]

Regression of instance boundary by aggregated CNN and GCN main figure

Regression of Instance Boundary by Aggregated CNN and GCN

Yanda Meng, Meng Wei, Dongxu Gao, Yitian Zhao, Xiaoyun Yang, Xiaowei Huang, Yalin Zheng

ECCV 2020 [Paper]

Education

Experience

Viridien

Machine Learning Engineer Intern, Jun 2021 - Feb 2022

Worked on 3D vision for seismic imaging, synthetic data generation, and AI-assisted geoscience workflows.

UCLA

Summer Research Intern, Jul 2019 - Sep 2019

Developed deep learning methods for hemorrhagic stroke detection and segmentation on CT images. Supervised by Dr. Fabien Scalzo and Prof. David S Liebeskind.

Honors

Review Services